Telematics combined actuarial neural networks for cross-sectional and longitudinal claim count data
The paper provides novel cross-sectional and longitudinal claim count models for vehicle insurance. The architecture of these models is based on a combined actuarial neural network (CANN), that combines classical actuarial models with a neural network. This approach takes advantage of the main features of classical models, as well as the flexibility and the capacity to capture intricate relationships provided by the neural network. After presenting two datasets, that is the contract dataset and the telematics dataset, the CANN claim count models are discussed in depth and then applied to specific dataset. Model performance is extensively analyzed.
- Actuarial intelligence in auto insurance: claim frequency modeling with driving behavior features and improved boosted trees
- JOINT MODELING OF CLAIM FREQUENCIES AND BEHAVIORAL SIGNALS IN MOTOR INSURANCE
- Improving automobile insurance claims frequency prediction with telematics car driving data
- Micro-level prediction of outstanding claim counts based on novel mixture models and neural networks
- Enhanced gradient boosting for zero-inflated insurance claims and comparative analysis of CatBoost , XGBoost , and LightGBM
- Actuarial Modelling of Claim Counts
- Autocalibration and Tweedie-dominance for insurance pricing with machine learning
- Bias regularization in neural network models for general insurance pricing
- Claims frequency modeling using telematics car driving data
- Covariate selection from telematics car driving data
- Deep learning
- Feature extraction from telematics car driving heatmaps
- Improving automobile insurance claims frequency prediction with telematics car driving data
- Neural network embedding of the over-dispersed Poisson reserving model
- Regression analysis of count data
- Statistical foundations of actuarial learning and its applications
- The balance property in neural network modelling
- The use of annual mileage as a rating variable
- Detection of interacting variables for generalized linear models via neural networks
- Enhancing actuarial non-life pricing models via transformers
- Enhanced gradient boosting for zero-inflated insurance claims and comparative analysis of CatBoost , XGBoost , and LightGBM
- An observation-driven state-space count model for experience rating
This page was built for publication: Telematics combined actuarial neural networks for cross-sectional and longitudinal claim count data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6556599)
